Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor

Sayandeep Acharya, William M. Mongan, Ilhaan Rasheed, Yuqiao Liu, Endla Anday, Genevieve DIon, Adam Fontecchio, Timothy Kurzweg, Kapil R. Dandekar

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Objective: Utilizing passive radio frequency identification (RFID) tags embedded in knitted smart-garment devices, we wirelessly detect the respiratory state of a subject using an ensemble-based learning approach over an augmented Kalman-filtered time series of RF properties. Methods: We propose a novel approach for noise modeling using a 'reference tag,' a second RFID tag worn on the body in a location not subject to perturbations due to respiratory motions that are detected via the primary RFID tag. The reference tag enables modeling of noise artifacts yielding significant improvement in detection accuracy. The noise is modeled using autoregressive moving average (ARMA) processes and filtered using state-augmented Kalman filters. The filtered measurements are passed through multiple classification algorithms (naive Bayes, logistic regression, decision trees) and a new similarity classifier that generates binary decisions based on current measurements and past decisions. Results: Our findings demonstrate that state-augmented Kalman filters for noise modeling improves classification accuracy drastically by over 7.7% over the standard filter performance. Furthermore, the fusion framework used to combine local classifier decisions was able to predict the presence or absence of respiratory activity with over 86% accuracy. Conclusion: The work presented here strongly indicates the usefulness of processing passive RFID tag measurements for remote respiration activity monitoring. The proposed fusion framework is a robust and versatile scheme that once deployed can achieve high detection accuracy with minimal human intervention. Significance: The proposed system can be useful in remote noninvasive breathing state monitoring and sleep apnea detection.

Original languageEnglish (US)
Article number8416727
Pages (from-to)1022-1031
Number of pages10
JournalIEEE Journal of Biomedical and Health Informatics
Volume23
Issue number3
DOIs
StatePublished - May 2019

Fingerprint

Radio Frequency Identification Device
Radio frequency identification (RFID)
Noise
Learning
Kalman filters
Respiration
Classifiers
Fusion reactions
Decision Trees
Clothing
Monitoring
Sleep Apnea Syndromes
Electric current measurement
Decision trees
Artifacts
Logistics
Time series
Logistic Models
Equipment and Supplies
Processing

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management

Cite this

Acharya, S., Mongan, W. M., Rasheed, I., Liu, Y., Anday, E., DIon, G., ... Dandekar, K. R. (2019). Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor. IEEE Journal of Biomedical and Health Informatics, 23(3), 1022-1031. [8416727]. https://doi.org/10.1109/JBHI.2018.2857924
Acharya, Sayandeep ; Mongan, William M. ; Rasheed, Ilhaan ; Liu, Yuqiao ; Anday, Endla ; DIon, Genevieve ; Fontecchio, Adam ; Kurzweg, Timothy ; Dandekar, Kapil R. / Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor. In: IEEE Journal of Biomedical and Health Informatics. 2019 ; Vol. 23, No. 3. pp. 1022-1031.
@article{45d8e46dc6bc4268a5d351ee2b8711b7,
title = "Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor",
abstract = "Objective: Utilizing passive radio frequency identification (RFID) tags embedded in knitted smart-garment devices, we wirelessly detect the respiratory state of a subject using an ensemble-based learning approach over an augmented Kalman-filtered time series of RF properties. Methods: We propose a novel approach for noise modeling using a 'reference tag,' a second RFID tag worn on the body in a location not subject to perturbations due to respiratory motions that are detected via the primary RFID tag. The reference tag enables modeling of noise artifacts yielding significant improvement in detection accuracy. The noise is modeled using autoregressive moving average (ARMA) processes and filtered using state-augmented Kalman filters. The filtered measurements are passed through multiple classification algorithms (naive Bayes, logistic regression, decision trees) and a new similarity classifier that generates binary decisions based on current measurements and past decisions. Results: Our findings demonstrate that state-augmented Kalman filters for noise modeling improves classification accuracy drastically by over 7.7{\%} over the standard filter performance. Furthermore, the fusion framework used to combine local classifier decisions was able to predict the presence or absence of respiratory activity with over 86{\%} accuracy. Conclusion: The work presented here strongly indicates the usefulness of processing passive RFID tag measurements for remote respiration activity monitoring. The proposed fusion framework is a robust and versatile scheme that once deployed can achieve high detection accuracy with minimal human intervention. Significance: The proposed system can be useful in remote noninvasive breathing state monitoring and sleep apnea detection.",
author = "Sayandeep Acharya and Mongan, {William M.} and Ilhaan Rasheed and Yuqiao Liu and Endla Anday and Genevieve DIon and Adam Fontecchio and Timothy Kurzweg and Dandekar, {Kapil R.}",
year = "2019",
month = "5",
doi = "10.1109/JBHI.2018.2857924",
language = "English (US)",
volume = "23",
pages = "1022--1031",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

Acharya, S, Mongan, WM, Rasheed, I, Liu, Y, Anday, E, DIon, G, Fontecchio, A, Kurzweg, T & Dandekar, KR 2019, 'Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor', IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 3, 8416727, pp. 1022-1031. https://doi.org/10.1109/JBHI.2018.2857924

Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor. / Acharya, Sayandeep; Mongan, William M.; Rasheed, Ilhaan; Liu, Yuqiao; Anday, Endla; DIon, Genevieve; Fontecchio, Adam; Kurzweg, Timothy; Dandekar, Kapil R.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 23, No. 3, 8416727, 05.2019, p. 1022-1031.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Ensemble Learning Approach via Kalman Filtering for a Passive Wearable Respiratory Monitor

AU - Acharya, Sayandeep

AU - Mongan, William M.

AU - Rasheed, Ilhaan

AU - Liu, Yuqiao

AU - Anday, Endla

AU - DIon, Genevieve

AU - Fontecchio, Adam

AU - Kurzweg, Timothy

AU - Dandekar, Kapil R.

PY - 2019/5

Y1 - 2019/5

N2 - Objective: Utilizing passive radio frequency identification (RFID) tags embedded in knitted smart-garment devices, we wirelessly detect the respiratory state of a subject using an ensemble-based learning approach over an augmented Kalman-filtered time series of RF properties. Methods: We propose a novel approach for noise modeling using a 'reference tag,' a second RFID tag worn on the body in a location not subject to perturbations due to respiratory motions that are detected via the primary RFID tag. The reference tag enables modeling of noise artifacts yielding significant improvement in detection accuracy. The noise is modeled using autoregressive moving average (ARMA) processes and filtered using state-augmented Kalman filters. The filtered measurements are passed through multiple classification algorithms (naive Bayes, logistic regression, decision trees) and a new similarity classifier that generates binary decisions based on current measurements and past decisions. Results: Our findings demonstrate that state-augmented Kalman filters for noise modeling improves classification accuracy drastically by over 7.7% over the standard filter performance. Furthermore, the fusion framework used to combine local classifier decisions was able to predict the presence or absence of respiratory activity with over 86% accuracy. Conclusion: The work presented here strongly indicates the usefulness of processing passive RFID tag measurements for remote respiration activity monitoring. The proposed fusion framework is a robust and versatile scheme that once deployed can achieve high detection accuracy with minimal human intervention. Significance: The proposed system can be useful in remote noninvasive breathing state monitoring and sleep apnea detection.

AB - Objective: Utilizing passive radio frequency identification (RFID) tags embedded in knitted smart-garment devices, we wirelessly detect the respiratory state of a subject using an ensemble-based learning approach over an augmented Kalman-filtered time series of RF properties. Methods: We propose a novel approach for noise modeling using a 'reference tag,' a second RFID tag worn on the body in a location not subject to perturbations due to respiratory motions that are detected via the primary RFID tag. The reference tag enables modeling of noise artifacts yielding significant improvement in detection accuracy. The noise is modeled using autoregressive moving average (ARMA) processes and filtered using state-augmented Kalman filters. The filtered measurements are passed through multiple classification algorithms (naive Bayes, logistic regression, decision trees) and a new similarity classifier that generates binary decisions based on current measurements and past decisions. Results: Our findings demonstrate that state-augmented Kalman filters for noise modeling improves classification accuracy drastically by over 7.7% over the standard filter performance. Furthermore, the fusion framework used to combine local classifier decisions was able to predict the presence or absence of respiratory activity with over 86% accuracy. Conclusion: The work presented here strongly indicates the usefulness of processing passive RFID tag measurements for remote respiration activity monitoring. The proposed fusion framework is a robust and versatile scheme that once deployed can achieve high detection accuracy with minimal human intervention. Significance: The proposed system can be useful in remote noninvasive breathing state monitoring and sleep apnea detection.

UR - http://www.scopus.com/inward/record.url?scp=85050378052&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050378052&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2018.2857924

DO - 10.1109/JBHI.2018.2857924

M3 - Article

C2 - 30040664

AN - SCOPUS:85050378052

VL - 23

SP - 1022

EP - 1031

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 3

M1 - 8416727

ER -